I found the WebSocket and streaming use to be a lot easier and more consistent with Deepgram, which I also found better for multilingual use. The quality of the model is great, and the streaming functionality is awesome. I appreciated how the API is pretty easy to use, and some of the documentation is helpful. The ease of integration was something I liked, and the $200 free credits gave me a chance to test the quality of the platform, which was cool and provided some return. Review collected by and hosted on G2.com.

I think Deepgram needs to support more languages. It didn't work well with multilingual users speaking multiple languages in the same sentence, which is an issue for my European customers. Also, the real-time transcript doesn't handle voice commands properly, saying 'comma' instead of adding punctuation. It would be great to have low latency like Mac dictation for ease of use. Review collected by and hosted on G2.com.

I love Deepgram for a few reasons. First, their models are phenomenally accurate, which is vital for my extensive speech-to-text applications. I appreciate the flag option they provide to opt out of all data logging, which is super convenient compared to AssemblyAI, where you have to send an email to opt out of model training. I absolutely love the streaming option they have; I get live streaming feedback every second, and that makes it very enjoyable to use. The initial setup was absolutely smooth, and there was virtually no effort involved. I've tried many APIs, and Deepgram's setup was exactly what I expected. Review collected by and hosted on G2.com.

I think one aspect where Deepgram definitely needs to improve is that it heavily penalizes users from opting out of model training program. What they say is that they directly cost you twice as much if you opt out of model training. I think this is slightly unfair and the multiplier should have been less extreme. I think it's fair to cost about 25% to 50% more, but not 100% more. Other than that, I have one feedback for Deepgram. I think it's high time that they release a new model because the landscape is very competitive right now, assembly AI has introduced a newer model and 11 labs has introduced a newer model too. So I hope they introduce a new newer model too because that is how the landscape is evolving. Review collected by and hosted on G2.com.

I use Deepgram for the STT and TTS engine in my Goddo project, an AI buddy for kids, and I really appreciate its excellent latency. The STT transcription is very fast and quickly pushes to the LLM to generate a response, which is crucial for maintaining the kids’ interest. The voices in the TTS are decent and expressive. The $200 credit has been awesome since I haven't spent a single dollar on the Deepgram API so far, allowing me to test it heavily without worrying about the budget. Deepgram is better for my budget compared to other real-time APIs like Cartesia and Rime, which are too expensive. The per-minute cost will be affordable even after the credits are gone. The main things I like about Deepgram are the generous $200 credit and the decent latency, which is fast enough for kids who lack patience. The documentation is very clean and clear, making the setup straightforward. Review collected by and hosted on G2.com.

I think multilingual support is a big problem. The STT does a very good job in transcribing different languages and it's as quick as just English, so the multilingual part is good for STT. However, for TTS, it's a big problem. That is where I end up using Gemini Live Audio because that same voice can do different languages while maintaining the accent and pronunciation. That is definitely something that's missing from Deepgram. Review collected by and hosted on G2.com.

I use Deepgram for speech-to-text transcripts in English and German. I find that Deepgram processes quickly with very limited mistakes, even when there's an accent or background noise. I like that it's super easy to use, simple to set up with clear access to the API key, and offers dashboards to monitor usage in real-time. The clear UI and great UX make it even better. I make sure to keep an eye on how much my clients use the product by looking into the dashboard. I don’t have much time to scout for information in other places, so I just open Deepgram and always find what I need. The initial setup took less than 5 minutes, which was fantastic. I'm so happy to have Deepgram; it's great and provides a better quality of speech recognition than the previous solution we used, even with accents and background noise. Review collected by and hosted on G2.com.

I get several promo offers coming to my email. I wish there was a central repository with the offers so I can decide when I look into them. Review collected by and hosted on G2.com.

Deepgram is one of the best platform I have used for SST. Their new model, DeepGram Flux, is top in class; the way it handles end-of-turns compared to other platforms is superb, and their integration is also available with most tools and platforms, for example Pipecat supports DeepGram, Vapi has integration with DeepGram, and so on. I am using it on an everyday basis and on multiple projects, it's also being used on our production app. They also provide a good amount of free credits, which is super helpful in the beginning while experimenting. Review collected by and hosted on G2.com.

As of now, I don't have any issues with Deepgram; it's providing me with everything I am looking for. Review collected by and hosted on G2.com.

I use Deepgram to convert spoken audio into highly accurate, real-time text transcripts. I love that Deepgram provides ultra-low latency and developer-friendly APIs, making it incredibly easy to integrate high-accuracy, real-time transcription into modern tech stacks. The value of Deepgram lies in how it minimizes the 'friction' between capturing audio and generating usable data. Its ultra-fast, real-time speech-to-text capability handles noisy audio and diverse accents with ease. For high-stakes or interactive applications, the specific features of latency and API design change the entire development experience. Modern SDKs also make setup simple, like using the Node.js SDK which is very clean and straightforward. Review collected by and hosted on G2.com.

While Deepgram is highly efficient, its accuracy can sometimes dip with very heavy background noise or highly specialized technical jargon without custom model tuning. Review collected by and hosted on G2.com.

I like that Deepgram provides free and user-friendly APIs, which are essential for building my English learning app. The high-quality STT and TTS features they offer are really helpful, as they allow the app to support both audio and video understanding as well as user interaction with AI agents. The initial setup was also very easy, thanks to well-designed documentation, making it straightforward to get started. Review collected by and hosted on G2.com.

I think Deepgram could offer some high-level abstraction or SDKs to make it easier to deploy to different platforms. It would be helpful to have tools that wrap the STT and TTS for easier integration into our apps and across different frameworks. Review collected by and hosted on G2.com.

Deepgram provides TTS and STT all at a place, the transcription works pretty well, With high accuracy. Api documentation is sok good it's easier to integrate Deepgram in the voice agents. Review collected by and hosted on G2.com.

Pricing can get expensive at scale, While it's TTS is strongest part of it, STT is on the weaker side as it doesn't have many languages support so you might wanna integrate other TTS software to it Review collected by and hosted on G2.com.

I really like how Deepgram is significantly cheaper than competing providers. The diarization works well, which I appreciate. I find that Claude Code and Codex can easily use the API, making it a seamless experience. It's fast, and I was able to start processing a large amount of audio within minutes, which was great for my time-sensitive project. The accuracy is excellent, making Deepgram my preferred provider. The initial setup with my agent in Claude Code was super easy, and it handled everything quickly. The API access has made transcribing tons of stuff much faster, more easily, and more cheaply compared to the manual and piecemeal approach we used before with Otter. Review collected by and hosted on G2.com.

I have not had any issues. Review collected by and hosted on G2.com.

Deepgram’s APIs are quite easy to integrate, and the pricing model also makes it easier to scale. Review collected by and hosted on G2.com.

There are very limited Hindi voice options available in the TTS feature. Review collected by and hosted on G2.com.